Zotero MCP 690b30ff

MCP数据服务

提供方 alisoroushmd

数据服务 stdio · 本地进程 无需鉴权 社区 / 第三方 Claude DesktopClaude
查看接入方式

一个让AI助手能够搜索、创建、组织并引用Zotero文献库的MCP服务器,具备查重、引文分析和知识图谱构建功能。

一句话选型结论

按资料字段整理

Zotero MCP 690b30ff 属于数据服务类 MCP 服务器,stdio · 本地进程,无需鉴权,可直接接入 Claude Desktop、Claude,有可直接执行的安装命令。接入前先确认权限范围;涉及写入、删除或付款的操作,建议先在测试环境验证。

分类数据服务 传输方式stdio · 本地进程 鉴权无需鉴权 部署方式本地部署
GitHub 星标 3 仓库热度,无公开仓库时显示未标注
工具数 36 暴露给模型的工具数量
资源 / 提示词 0 / 0 资源与提示词模板数量
维护方 社区 / 第三方 核验等级 仅资料核对

工具与能力

数据服务
数量来自来源目录的标注,具体工具清单以官方文档为准
工具数量36暴露给模型可调用的工具个数
资源数量0可读取的资源条目
提示词数量0内置提示词模板数量

能力标签

支持客户端

适用场景

文献管理Python本地部署学术研究知识图谱引文分析AI集成

安装与配置

stdio · 本地进程 无需鉴权
客户端在本机拉起子进程,数据不出本机
pip install -e ".[graph,fulltext]"

这条命令只是入口,具体启动参数请按官方文档补齐,不要直接照搬到别的服务器。

  1. 1
    准备运行环境

    stdio 服务在本地起进程,需要先装好 Node.js 等运行时,再按安装命令拉取依赖。

  2. 2
    安装服务

    复制上面的安装命令执行;命令里带占位符的位置,换成自己的密钥或路径。

  3. 3
    写入客户端配置

    在客户端的 MCP 配置里填好启动命令和参数,保存后完全退出客户端再打开,让新配置生效。

  4. 4
    验证是否可用

    连接成功后客户端会列出约 36 个工具,随便调一个只读工具确认能返回结果。

典型使用场景

3 类
按分类与标签整理的常见用法,具体以官方文档为准
数据库查询

用自然语言查库、取数,不用手写 SQL。

数据同步与清洗

把多来源数据拉到一处做整理。

报表取数

按口径快速拉出统计结果。

选择建议

选之前先看这几条
按条目字段给出的判断,不替你决定用不用

值得选的地方

  • 资料标注 36 个工具,覆盖面较广,能满足多种调用。
  • 有现成的安装命令,不用自己找入口,照着跑就能起服务。
  • 已适配 Claude Desktop、Claude,换客户端不用重新研究配置。
  • 资料标注无需鉴权,装好就能连。

先想清楚的地方

  • stdio 方式要求本地装好运行时(如 Node.js),换机器要重新装一遍。
  • 版本更新与行为细节以官方仓库为准。

更适合

  • 需要在数据服务场景里让模型直接调用外部能力的人。
  • 已经在用 Claude Desktop、Claude 的用户,接入路径最短。
  • 想先快速试一下、能接受在本地或自有环境跑服务的人。

不太适合

  • 完全不想在本地装环境的人。
  • 需要厂商级 SLA 和技术支持的生产环境。

同类对比

6 个同类
同分类里挑最接近的几条,字段以各自详情页为准
MCP 服务器工具数传输方式部署方式安装命令最后核验
Zotero MCP 690b30ff当前 36 stdio · 本地进程 本地部署 有 2026-05-17
Memory 9d25f64e 9 未标注 未标注 无 2026-05-17
Getzep MCP 9 stdio · 本地进程 本地部署 有 2026-05-17
anything-llm 未标注 stdio · 本地进程 本地部署 有 2026-04-11
Prisma MCP Server 未标注 stdio · 本地进程 本地部署 有 2026-05-17
Astr Bot 未标注 stdio · 本地进程 本地部署 有 2026-05-17

服务器档案

数据服务
字段来自项目仓库与公开索引,中文说明由本站标注
提供方alisoroushmd上游标注的维护方 alisoroushmd
分类数据服务本站按上游分类展示
连接方式stdio · 本地进程客户端在本机拉起子进程,数据不出本机
鉴权方式无需鉴权远程服务建议用最小权限凭据
维护方社区 / 第三方核验等级 仅资料核对
包名 / 运行时未标注 · 未标注本地安装时用到的包标识与运行时
部署类型本地部署上游给出的部署形态
最近核验2026-05-17上游最后核验时间

详细介绍

20.3 KB
来自项目仓库与上游目录的原文,未做删改

zotero-mcp

MCP server that lets AI assistants search, create, organize, and cite from a Zotero library. Produces Word documents with live Zotero field codes. Checks for retractions, finds duplicates, maps citation graphs, and builds a knowledge graph with paper recommendations.

Quickstart

Add to your MCP client config (Claude Code, Claude Desktop, etc.):```json
{
"zotero": {
"command": "uvx",
"args": ["zotero-mcp-plus"],
"env": {
"ZOTERO_API_KEY": "your-api-key",
"ZOTERO_USER_ID": "your-user-id"
}
}
}


Get your API key and user ID at zotero.org/settings/keys.

**`OPENALEX_API_KEY` is also required for the analysis tools** (`check_retractions`, `get_citation_graph`, `check_published_versions`). To enable those plus the knowledge graph and full-text search tools, add the extras and an OpenAlex key:```json
{
  "zotero": {
    "command": "uvx",
    "args": ["zotero-mcp-plus[graph,fulltext]"],
    "env": {
      "ZOTERO_API_KEY": "your-api-key",
      "ZOTERO_USER_ID": "your-user-id",
      "OPENALEX_API_KEY": "your-openalex-key"
    }
  }
}

Free OpenAlex key at openalex.org/users/me.

Operating modes

All 39 tools work with just API credentials — Zotero desktop does not need to be running. Two diagnostic tools (check_ssl_health, audit_local_keys) require no credentials at all.

Mode What it provides Requirements
Cloud (primary) All reads, writes, citations, attachments, analysis, fulltext, entities ZOTERO_API_KEY + ZOTERO_USER_ID env vars
Local (optional) Faster reads via Zotero desktop's local API (no rate limits) Zotero 7 desktop running with local API enabled

When Zotero desktop is running, reads automatically use the faster local API. When it is not, reads fall back to the Web API transparently.

Call server_status to check which modes are available.

Tools

Read tools

Tool Description
server_status Check which modes are available
search_items Search library items by keyword
get_item Fetch item metadata or BibTeX
get_collections List all collections
get_collection_items List items in a collection
get_notes List child notes on an item
get_item_attachments List attachments with availability status
get_pdf_content Find best path to a paper's full text (PMCID, local PDF, or web download). Pass extract_text=true for inline text

Write tools

Tool · Description
create_item · Create item from DOI, PMID, or URL (with duplicate detection)
create_item_manual · Create item with manual metadata (with duplicate detection)
create_note · Attach a note to an item
create_collection · Create a collection
batch_organize · Bulk-add tags/collection to items
add_to_collection · Add item to a collection
update_item · Patch metadata fields
attach_pdf · Attach a local or auto-downloaded PDF
trash_items · Move items to trash (reversible)
inspect_trash · List trash contents — call before empty_trash
empty_trash · Permanently delete all trashed items (global, irreversible)
plan_attachment_migration · Dry-run plan for converting cloud attachments to linked files
migrate_attachments · Convert cloud attachments to linked files (dry run unless apply=true)
manage_tags · List, remove, or rename tags library-wide (action="list\ · remove\ · rename")

Citation tools

Tool Description
write_cited_document Create new .docx with live Zotero citations
insert_citations Insert citations into existing .docx

Analysis tools

Tool Description
check_retractions Check items for retractions, corrections, and errata via CrossRef + OpenAlex
find_duplicates Scan library for duplicate items by DOI and title similarity
get_citation_graph Get citing/referenced works via OpenAlex with in-library flags
check_published_versions Check if preprints have been formally published; reports journal and in-library status

Knowledge graph tools

Requires the graph extra (uvx "zotero-mcp-plus[graph]" or pip install "zotero-mcp-plus[graph]") and OPENALEX_API_KEY env var.

Tool · Description
build_index · Build or update citation graph and/or fulltext index (type="graph\ · fulltext\ · both")
query_knowledge_graph · PageRank, clusters, bridge papers, shortest paths, neighborhood, timeline, topic evolution, citation velocity, trending
find_related_papers · Semantic Scholar recommendations from library seeds (like Connected Papers)
query_authors · Prolific/influential authors, co-author lookup, ego network, author clusters
export_knowledge_graph · Interactive HTML visualization (citations, authors, or full view) with D3.js

Full-text search tools

Requires the fulltext extra (uvx "zotero-mcp-plus[fulltext]" or pip install "zotero-mcp-plus[fulltext]").

Tool Description
search_fulltext Search indexed full text with BM25 ranking and highlighted snippets

Use build_index(type='fulltext') to extract text from library PDFs and build the FTS5 search index.

Entity extraction tools

Two-tool pattern: the MCP server provides abstracts, the calling LLM extracts entities, and stores them back.

Tool Description
get_unextracted_abstracts Get papers with abstracts not yet entity-extracted
store_entities Persist typed entities (biomarker, drug, gene, etc.) extracted by the LLM
search_entities Query entity index: by_name, by_type, paper_entities (by DOI), co_occurrence, shared_entities

Diagnostic tools

These two tools require no API credentials and can be used to debug setup problems.

Tool Description
check_ssl_health Diagnose Python SSL/TLS config — cert paths, CA count, env-var overrides, live HTTPS probes. Returns HEALTHY/DEGRADED/BROKEN verdict with remediation steps. Use when any tool reports CERTIFICATE_VERIFY_FAILED.
audit_local_keys Scan local Zotero SQLite for item/collection keys containing characters (0, 1, O) that the Zotero sync server rejects, halting sync.

MCP Prompts

Pre-built multi-tool workflows that guide the AI through common tasks:

Prompt Description
literature_audit Check retractions, verify preprint publication status, scan for duplicates
build_and_explore Build indexes and explore research landscape (influential papers, clusters, trends)
add_and_verify Add a paper, check retractions, attach PDF, find related work
extract_entities Extract biomedical entities from unprocessed abstracts and store them

Writing with live citations

Both document tools use [@ITEM_KEY] markers in content:```text
Gastric cancer screening reduces mortality [@ABC123]. Multiple studies
support this finding [@DEF456, @GHI789].


- `write_cited_document` creates a new .docx from markdown
- `insert_citations` modifies an existing .docx (preserves formatting, including tables)
- Citations are emitted as Vancouver-style superscript numbers
- A References section with a live Zotero bibliography field is appended

After opening in Word with the Zotero plugin: click Refresh to populate the bibliography and switch citation styles.

## Reclaiming Zotero cloud storage quota

`attach_pdf` writes linked files by default, so it no longer consumes quota.
Attachments created *before* that change are still imported (cloud-stored) and
still count against it. `zotero-migrate-attachments` converts `imported_file`
attachments in place by default: each file is copied or downloaded to local
disk, hash-verified, replaced with a `linked_file` attachment on the same parent
item, and the original is trashed.

Always start with the dry run — it is the default, and writes nothing:```bash
zotero-migrate-attachments

Read the plan, then convert a small batch first:```bash
zotero-migrate-attachments --apply --modes imported_file --limit 5


Check that those five items look right in Zotero (the PDF should open, and the
attachment icon shows a link), then run the rest:```bash
zotero-migrate-attachments --apply

Trashing is reversible and the quota is not returned until the trash is
emptied. The migration records its keys in
.zotero-attachment-migration-trash.json under the destination directory
before trashing anything. DELETE /items/trash is global, so review the trash,
then use the separate purge-only invocation:```bash
zotero-migrate-attachments --apply --empty-trash


That loads the keys persisted by the earlier invocation and refuses to run if
the trash holds anything the migration did not put there. If `--dest` was used
for migration, pass the same `--dest` here. The command never infers ownership
from whatever happens to be in the trash.

`imported_url` snapshots are excluded by default because one Zotero snapshot
can contain an HTML file plus companion resources. To opt in, use
`--modes imported_url`; even then, a snapshot is migrated only when it is
already downloaded locally and its storage directory contains exactly one
regular file. Cloud-only or multi-resource snapshots are skipped rather than
flattened and damaged.

Useful flags: `--modes imported_file` (the default), `--modes imported_url`
(explicit validated-snapshot opt-in), `--dest DIR` (default
`/linked-attachments`), `--no-trash` (create the links now,
trash later), `--include-local-only` (also convert attachments Zotero holds no
cloud file for — these free no quota), and `--limit N`.

The same operations are exposed as MCP tools: `plan_attachment_migration`,
`migrate_attachments`, `inspect_trash`.

**Back up the linked-attachment directory.** Linked files do not sync; after
migrating, those bytes exist only on this machine.

## Architecture```text
┌─────────────┐  reads+writes  ┌──────────────────┐
│  MCP client │ ──────────────>│ Zotero Web API   │
│             │                │ api.zotero.org   │
│             │  reads (fast)  ├──────────────────┤
│             │ ─ ─ ─ ─ ─ ─ ─>│ Zotero Desktop   │
│             │    (optional)  │ localhost:23119  │
│             │   resolves     ├──────────────────┤
│             │ ──────────────>│ Translation Srv  │
│             │                │ PubMed/CrossRef  │
│             │   analysis     ├──────────────────┤
│             │ ──────────────>│ OpenAlex         │
│             │                │ CrossRef updates │
│             │  knowledge     ├──────────────────┤
│             │  graph + FTS5  │ SQLite + NetworkX│
│             │                │ (local cache)    │
│             │  related       ├──────────────────┤
│             │  papers        │ Semantic Scholar │
└─────────────┘                └──────────────────┘

Setup

1. Create a Zotero Web API key (required)

  1. Go to zotero.org/settings/keys
  2. Create a key with write access to your library
  3. Copy the API key and note your User ID

2. Enable Zotero's local API (optional, for faster reads)

In Zotero Desktop: Settings > Advanced > General > enable Allow other applications on this computer to communicate with Zotero. This is optional — without it, all reads go through the Web API.

3. Install

Option A — uvx (recommended, no clone needed):

Install uv first if you don't have it: astral.sh/uv (one-line install on macOS/Linux). Then use zotero-mcp-plus for the base install or zotero-mcp-plus[graph,fulltext] for the full feature set (see Quickstart above). Your MCP client runs uvx directly — no separate install step.

Option B — local install:```bash
git clone https://github.com/alisoroushmd/zotero-mcp.git
cd zotero-mcp
pip install -e ".[graph,fulltext]"


Then configure your MCP client to run `python -m zotero_mcp`.

**Developing against a live install (uvx + local source):**

If your MCP client runs the server via `uvx --from 'zotero-mcp-plus @ file:///path/to/zotero-mcp'` (or any `file://` reference to this checkout), be aware that **uvx builds a wheel once and caches it**. Editing the source afterwards silently does nothing — the running server keeps using the cached wheel until either:

- the `version` in `pyproject.toml` is bumped (a new version → a new cache entry), or
- the cache is invalidated explicitly: `uvx --reinstall --from '…' zotero-mcp` for one run, or `uv cache clean zotero-mcp-plus` to purge it.

Either way, the MCP client must then be fully restarted (not just reconnected) so it launches a fresh server process. If a fix you just made doesn't seem to take effect, this cache is almost always why. For rapid iteration, prefer Option B (`pip install -e`) — editable installs pick up source edits on every server start with no cache in the way.

### 4. Set up OpenAlex API key (required for analysis and knowledge graph tools)

`OPENALEX_API_KEY` is required for: `check_retractions`, `get_citation_graph`, `check_published_versions`, `build_index(type='graph')`, `query_knowledge_graph`, `query_authors`, and `export_knowledge_graph`. OpenAlex requires a free API key as of Feb 2026:

1. Register at openalex.org/users/me
2. Set `OPENALEX_API_KEY` in your MCP client config

### 5. Install knowledge graph support (optional)

With uvx (add to your MCP client config `args`):```text
zotero-mcp-plus[graph]

With pip (local install):```bash
pip install "zotero-mcp-plus[graph]"


Adds networkx, numpy, and scipy for `build_index(type='graph')`, `query_knowledge_graph`, `query_authors`, and `export_knowledge_graph`. `find_related_papers` works without it (uses Semantic Scholar API directly).

Optionally set `SEMANTIC_SCHOLAR_API_KEY` for improved rate limits.

### 6. Install full-text search support (optional)

With uvx (add to your MCP client config `args`):```text
zotero-mcp-plus[fulltext]

With pip (local install):```bash
pip install "zotero-mcp-plus[fulltext]"


Adds pypdf for extracting text from PDFs. Used by `build_index(type='fulltext')` to build a searchable FTS5 index. Without it, `search_fulltext` and `build_index(type='fulltext')` return an install prompt.

## Environment variables

| Variable                   | Required | Description |
| -------------------------- | -------- | ----------- |
| `ZOTERO_API_KEY`           | Yes      | Zotero Web API key — get at zotero.org/settings/keys |
| `ZOTERO_USER_ID`           | Yes      | Zotero user/group ID — same page as the API key |
| `OPENALEX_API_KEY`         | For analysis/graph tools | Required for `check_retractions`, `get_citation_graph`, `check_published_versions`, and all knowledge-graph tools — free at openalex.org/users/me |
| `ZOTERO_MCP_EMAIL`         | No       | Your email address. Sent in User-Agent headers to CrossRef/OpenAlex polite pools and required for Unpaywall PDF lookup in `attach_pdf`. Without it, Unpaywall PDF fetches are skipped. |
| `SEMANTIC_SCHOLAR_API_KEY` | No       | Improves rate limits for `find_related_papers` — free at semanticscholar.org |
| `NCBI_API_KEY`             | No       | Raises the PubMed/eutils rate limit from 3 to 10 req/s — helps bulk identifier resolution and graph builds. Free at ncbi.nlm.nih.gov/account. |
| `ZOTERO_DATA_DIR`          | No       | Override path to Zotero desktop data directory (default: `~/Zotero`). Used by `audit_local_keys` and the local PDF path resolver in `get_pdf_content`. |
| `ZOTERO_LINKED_ATTACHMENT_DIR` | No   | Where `attach_pdf` writes PDFs for linked-file attachments (default: `/linked-attachments`). |
| `ZOTERO_ATTACHMENT_MODE`   | No       | `linked` (default) stores PDFs on local disk as `linked_file` attachments and consumes **no** Zotero cloud storage quota. `imported` uploads into Zotero storage instead — syncs across devices, but counts against the quota and fails with HTTP 413 once it is full. Linked-file attachments are not valid in group libraries; use `imported` there. |
| `ZOTERO_MCP_GRAPH_DB`      | No       | Override path for the knowledge-graph SQLite database (default: OS-native per-user data dir — `~/Library/Application Support/zotero-mcp/` on macOS, `%LOCALAPPDATA%\zotero-mcp\` on Windows, `~/.local/share/zotero-mcp/` elsewhere; an existing legacy `~/.local/share` DB is reused). |
| `ZOTERO_MCP_GRAPH_MATERIALIZATION_LIMIT` | No | Maximum combined persisted graph records loaded into NetworkX (papers, citations, topics, authors, and paper-author links). Defaults to `100000`; oversized graphs are refused before materialization to protect server memory. |
| `XDG_DATA_HOME`            | No       | Standard XDG override for the default graph DB location. |
| `PARENT_WATCHDOG_DISABLE`  | No       | Set to `1` to disable the orphan-process watchdog that kills the server when the parent process (Claude.app, uvx, etc.) exits. |

## Troubleshooting

| Problem | Cause | Fix |
| ------- | ----- | --- |
| `Cloud CRUD mode requires ZOTERO_API_KEY` | Missing env vars | Set `ZOTERO_API_KEY` and `ZOTERO_USER_ID` in your MCP client config |
| `CERTIFICATE_VERIFY_FAILED` on any tool | Python SSL misconfiguration | Run `check_ssl_health` — it diagnoses the cert bundle and returns remediation steps |
| `attach_pdf` never finds a free PDF | `ZOTERO_MCP_EMAIL` not set | Unpaywall requires a real email address. Set `ZOTERO_MCP_EMAIL` in your config. |
| Analysis tools fail without obvious error | `OPENALEX_API_KEY` missing | `check_retractions`, `get_citation_graph`, and `check_published_versions` all require it |
| Knowledge graph materialization is refused | The persisted graph exceeds the default 100,000-record in-memory safety ceiling | Reduce/rebuild the graph, or set `ZOTERO_MCP_GRAPH_MATERIALIZATION_LIMIT` higher only when the server has enough memory |
| Reads are slow | Zotero desktop not running; reads go through Web API | Start Zotero and enable local API for faster reads (optional) |
| Item not found after creation | Zotero sync lag | Items created via Web API appear locally after Zotero syncs (usually seconds) |
| `Version conflict for item` | Item was modified between read and write | Retry the operation; the server uses optimistic locking |
| Orphan server processes accumulate | Parent exits without closing stdin | Normal behavior is auto-handled by the watchdog. Disable with `PARENT_WATCHDOG_DISABLE=1` if it conflicts with your setup. |

## Development```bash
pip install -e ".[dev,graph,fulltext]"
python -m pytest tests/ -v

License

MIT

常见问题

8 问
答案由本站依据条目字段整理,不引用上游原文
Zotero MCP 690b30ff 怎么安装?

在客户端按下面的安装命令接入:pip install -e ".[graph,fulltext]"。装完在客户端配置里引用同一个包或端点。

Zotero MCP 690b30ff 怎么在 Claude Desktop、Claude 里配置?

它的传输方式是stdio · 本地进程,在客户端的 MCP 配置里填好启动命令和参数,保存后完全退出客户端再打开,配置才会生效。

Zotero MCP 690b30ff 收费吗?

本站不代收费用,也没有标注具体价格。是否收费取决于服务本身和背后的接口额度,正式使用前按官方说明确认。

Zotero MCP 690b30ff 需要 API Key 吗?

资料标注为无需认证,装好就能连;如果实际调用时报鉴权错误,按官方文档补上凭据。

Zotero MCP 690b30ff 支持哪些客户端?

资料标注支持 Claude Desktop、Claude;其他客户端只要能配置 MCP Server,也能用同样的命令或地址接入。

Zotero MCP 690b30ff 能提供哪些能力?

资料显示约 36 个工具;能力标签包括 文献管理、学术研究、Python、Claude。具体工具清单以官方文档为准。

Zotero MCP 690b30ff 需要什么运行环境?

属于本地进程,需要在本机装好运行环境。

Zotero MCP 690b30ff 是本地还是远程?

它是本地进程(stdio),由客户端在本机拉起。传输方式为stdio · 本地进程。

热门专题

按标签挑服务器
全部专题 →

服务器信息以作者仓库与官方文档为准;分类、传输方式与鉴权方式的中文说明为中文整理,最近核验 2026-05-17。